© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3976
    Prev
    Next
    INDEX
    Explanations

    animal studies, rodents, mice, rats

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects mentions of rodent animal models (e.g. “mice,” “mouse,” “rat,” “murine”) in scientific text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    0.81
    0.80
     Characteristics
    0.79
     Motivation
    0.71
     Definition
    0.67
     Einige
    0.67
     Emotional
    0.66
     avere
    0.64
    r
    0.64
     Wird
    0.64
    POSITIVE LOGITS
     животных
    0.96
     동물
    0.88
     반려동
    0.84
    팜
    0.82
    animals
    0.81
     hewan
    0.79
     валю
    0.78
    动物
    0.77
     hayvan
    0.77
     биологи
    0.76
    Activations Density 0.002%

    No Known Activations